Hi, I'm Jisu Shin!

I am a Research Scientist

Jisu Shin

PhD candidate in the Department of AI

I am a Ph.D. candidate in the Department of AI, GIST, advised by Prof. Hae-Gon Jeon. I am currently conducting my research at Yonsei University, South Korea.

My research lies in 3D Vision for human and scene understanding, particularly in modeling physical interactions and human cues for robotics and embodied AI. I am interested in building 3D representations of humans and environments that ground embodied perception, from digital twins and human-robot interaction to robot vision in the real world.

News

  • Sep 2026
    ComPose has been accepted at NeurIPS 2026! πŸŽ‰
  • Aug 2026
    Received the Best Presentation Award at the Doctoral Colloquium of KCCV 2026! πŸ†
  • Aug 2026
    Selected as an Outstanding Reviewer at ECCV 2026! πŸ†
  • Jul 2026
    R3G, PIAvatar, and From Script to Shot have been accepted at ECCV 2026! πŸŽ‰
  • Feb 2026
    Off the Grid has been accepted at CVPR 2026! πŸŽ‰
  • Jan 2026
    CHROMA has been accepted at ICLR 2026! πŸŽ‰
  • Jul 2025
    Attended the International Computer Vision Summer School (ICVSS) in Sicily, Italy! πŸ”₯
  • Jun 2025
    Video Color Grading via LUT Generation has been accepted at ICCV 2025! πŸŽ‰
  • Dec 2024
    Started a research internship at the 3D Vision Team, Huawei Noah's Ark Lab in the United Kingdom! πŸ”₯
  • Dec 2024
    Selected as a Finalist of the 2024 Qualcomm Innovation Fellowship Korea! πŸŽ‰
  • Jul 2024
    CanonicalFusion has been accepted at ECCV 2024! πŸŽ‰
  • Feb 2024
    Close Imitation of Expert Retouching has been accepted at CVPR 2024! πŸŽ‰
  • Jun 2023
    Started a research internship at KETI (Korea Electronics Technology Institute)! πŸ”₯
  • Feb 2023
    Received the Excellent Paper Award at the 29th International Workshop on Frontiers of Computer Vision (IW-FCV 2023)! πŸ†
  • Nov 2022
    Task-specific Scene Structure Representations has been accepted at AAAI 2023 as an Oral Presentation! πŸŽ‰
  • Mar 2021
    Started my Ph.D. at GIST! πŸ”₯

Research Interests

3D Vision and Digital Twin Systems

Human & Scene Reconstruction, 3D Gaussian Splatting, Physical World Modeling

Embodied Perception and Physical AI

Physically Interactive Avatars, Human Motion Modeling, Vision-based Perception for Robotic Systems and Edge AI Deployment

Computational Photography

Camera ISP Modeling, Image Restoration, Image Harmonization

Generative AI for Visual Content Creation

Diffusion-based Image/Video Enhancement, Video Color Grading

Publications

  • All
  • Under Review
  • Conference
  • Journal

Controllable Crowd Generation through World-Model Planning

JunGyu Lee, Jisu Shin, Seunghyun Shin, and Hae-Gon Jeon

Under Review

Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches

Sunjoo Whang, Jungjun Oh, Minsung Kim, Dongho Seo, Jisu Shin, Gregory Kielian, Hoi-Jun Yoo, and Sangjin Kim

Under Review

ComPose: When to Trust Hands for Object Pose Tracking

Jisu Shin, Junoh Lee, JunGyu Lee, Inhwan Bae, Dohyeon Lee, Hokyun Im, Youngwoon Lee, and Hae-Gon Jeon

Neural Information Processing Systems (NeurIPS), 2026

Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting

Junoh Lee, Junmyeong Lee, Yeon-Ji Song, Inhwan Bae, Jisu Shin, Hae-Gon Jeon, and Jin-Hwa Kim

European Conference on Computer Vision (ECCV), 2026

PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling

Sang-Hun Han, Min-Gyu Park, Jisu Shin, Seunghyun Shin, Jin-Hwi Park, and Hae-Gon Jeon

European Conference on Computer Vision (ECCV), 2026

From Script to Shot: A Benchmark for Grounding Screenplays in Movies

Jungu Cho, Young-Jae Park, Seong Jong Ha, Siyeol Kim, Seungho Park, Jisu Shin, Junmyeong Lee, Chaemin Hwang, Hyunjun Jung, Sangeyl Lee, and Hae-Gon Jeon

European Conference on Computer Vision (ECCV), 2026

Off the Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting

Arthur Moreau, Richard Shaw, Michal Nazarczuk, Jisu Shin, Thomas Tanay, Zhensong Zhang, Songcen Xu, Eduardo PΓ©rez-Pellitero

Computer Vision and Pattern Recognition (CVPR), 2026

CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction

Jisu Shin, Richard Shaw, Seunghyun Shin, Zhensong Zhang, Hae-Gon Jeon, Eduardo PΓ©rez-Pellitero

The Fourteenth International Conference on Learning Representations (ICLR), 2026

Video Color Grading via Look-Up Table Generation

Seunghyun Shin, Dongmin Shin, Jisu Shin, Hae-Gon Jeon, and Joon-Young Lee

International Conference on Computer Vision (ICCV), 2025

The path-tracing simulation of light-field camera system: SurfCam/GrainCams for lunar surface exploration

Minbae Kim, Minsup Jeong, Mingyeong Lee, Jihun Kim, Young-Jun Choi, Sungsoo S Kim, Hae-Gon Jeon, and Jisu Shin

Advances in Space Research, 2024

CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images

Jisu Shin, Junmyeong Lee, Seongmin Lee, Min-Gyu Park, Ju-Mi Kang, Ju Hong Yoon, and Hae-Gon Jeon

European Conference on Computer Vision (ECCV), 2024

Close Imitation of Expert Retouching for Black-and-White Photography

Seunghyun Shin, Jisu Shin, Jihwan Bae, Inwook Shim and Hae-Gon Jeon

Computer Vision and Pattern Recognition (CVPR), 2024

Task-specific Scene Structure Representations

Jisu Shin*, Seunghyun Shin*, and Hae-Gon Jeon (* equally contributed)

The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023 (Oral)

Scene Structure Guidance Network: Unfolding Graph Partitioning into Pixel-Wise Feature Learning

Jisu Shin, Seunghyun Shin, and Hae-Gon Jeon

Under Review

Experience & Education

Research Experience

Research Intern

Dec. 2024 - Sep. 2025

3D Vision Team, Huawei Noah's Ark Lab, United Kingdom

  • 3D Scene Reconstruction using Gaussian Splatting on Appearance Varying Environment

Research Intern

Jun. 2023 - March. 2024

KETI (Korea Electronics Technology Institute), Gyeonggi-do, South Korea

  • Drivable 3D Human Generation

Research Intern

Jun. 2019 - Aug. 2019

ETRI (Electronics and Telecommunications Research Institute), Daejeon, South Korea

  • Edge Computing & Computer Network

Education

PhD, Department of AI

2021 - Present

Gwangju Institute of Science and Technology, Gwangju, South Korea

Advisor: Prof. Hae-Gon Jeon

Bachelor of Electrical Engineering and Computer Science

2017 - 2021

Gwangju Institute of Science and Technology, Gwangju, South Korea

Advisor: Prof. Hae-Gon Jeon

Honors & Awards

Honors & Awards

  • Selected for the Doctoral Colloquium and received the Best Presentation Award, Korean Conference on Computer Vision (KCCV), Aug 2026
  • Selected as Outstanding Reviewer, European Conference on Computer Vision (ECCV), 2026
  • Travel Scholarship Funding - ICLR-26 Student Scholarship, Rio de Janeiro, Brazil, Apr 2026
  • Scholarship Funding - RA Student Research Achievement Scholarship, AI Graduate School, GIST, Dec 2025
  • Selected as the Participants for International Computer Vision Summer School (ICVSS), July 2025
  • Selected as Internship Program on 3D Vision Team at Huawei Noah's Ark Lab, United Kingdom, Dec 2024 ~ Sep 2025
  • Finalist, 2024 Qualcomm Innovation Fellowship Korea, Qualcomm Technologies, Inc., Dec 2024
  • 7th Hong Bok-Soon Scholarship, Development Foundation, GIST, Nov 2024.
  • Selected as Internship Program on Korea Electronics Technology Institute (KETI), Jun 2023 ~ Mar 2024
  • Travel Scholarship Funding - AAAI-23 Student Scholarship, Washington, DC, USA, Feb 2023
  • Excellent Paper Award, The 29th International Workshop on Frontiers of Computer Vision (IW-FCV 2023), Feb 2023
  • Selected as Internship Program on Electronics and Telecommunications Research Institute (ETRI), Jul 2019 ~ Aug 2019
  • Selected as Summer School Exchange Program Scholarship on UC Berkeley, Jun 2018 ~ Aug 2018

Academic Services

Conference Reviewer

  • Neural Information Processing Systems (NeurIPS) - 2026
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - 2024, 2025, 2026
  • IEEE/CVF European Conference on Computer Vision (ECCV) - 2026
  • International Conference on Learning Representations (ICLR) - 2026, 2027
  • The Association for the Advancement of Artificial Intelligence (AAAI) - 2025, 2026, 2027
  • British Machine Vision Conference (BMVC) - 2026

Journal Reviewer

  • Frontiers in Virtual Reality
  • Frontiers in AI - Machine Learning and Artificial Intelligence
  • Neural Networks, Elsevier

Press & Talks

Press Release

Sep 25, 2024

The article reports GIST's development of an animatable 3D human avatar from multiple images using forward skinning-based differentiable rendering.

Press Release

Jun 18, 2024

The article reports GIST's development of a aesthetic black and white photography retouching algorithm that mimics the style of photographer easily.

Admission Video

Mar 31, 2023

Interview with current student Jisu Shin, highlighting her publication experience in AI graduate school.

Contact

Yonsei University, Yonsei Engineering Research Park, Room 425a
Sinchon-dong, Seoul, Republic of Korea